Machine learning in trading: theory, models, practice and algo-trading - page 462
You are missing trading opportunities:
- Free trading apps
- Over 8,000 signals for copying
- Economic news for exploring financial markets
Registration
Log in
You agree to website policy and terms of use
If you do not have an account, please register
And I started to get interested, but I plan to manage a team of analysts and ML specialists, I need to be aware of what they do.
Why did you stop?
There was a trend Expert Advisor. A random forest took part in trend prediction in it. I do not believe that there will be trends. I have to trade deviations and this is GARCH.
There was a trend advisor. It had a random forest taking part in trend prediction. And I don't believe there will be trends ahead. You have to trade deviations, which is a GARCH.
So the final decision is based on "believe/don't believe"... And you believe the shit out of GARCH. Well, for now . But you might not.
So what do you do?
So the final decision is based on "believe/don't believe"... And you believe a shithead named GARCH. Well, for now . But you might not.
So what do you do?
I don't believe anything.
So BEFORE testing I try to get proof that my model will behave WITHOUT testing sample exactly as it does during testing. GARCH is full of tools for that. I am not interested in a TS, the future behavior of which is not determined.
But the ideology is fundamentally different from MO.
Machine Learning in Trading: Theory and Practice (Trading and Beyond)
To help theorists and practitioners:
I don't believe anything.
So BEFORE testing I try to get evidence that my model will behave WITHOUT the test sample exactly as it did during testing. GARCH is full of tools for this. I am not interested in a TS, the future behavior of which is not determined.
But the ideology is fundamentally different from MO.
So you have already played with scaffolding for several years. Now you will master the GARCH toy - this toy will be enough for a long time.
And no matter how cardinally different ideology is from MO, you'll need support in this business.
I don't believe anything.
So BEFORE testing I try to get evidence that my model will behave WITHOUT the test sample exactly as it does when tested. GARCH is full of tools for this. I am not interested in a TS, the future behavior of which is not determined.
But the ideology is fundamentally different from MO.
I've heard it 500 times already :) It's interesting to see a picture or results, not everything is so complicated in these models, a couple of months will be enough to understand if it works or not.
I would like to see a separate branch on this method or articles.)
I don't believe anything.
So BEFORE testing I try to get evidence that my model will behave WITHOUT the test sample exactly as it did during testing. GARCH is full of tools for this. I am not interested in a TS, the future behavior of which is not determined.
But the ideology is fundamentally different from MO.
The most ardent admirer of predicting the future is deflated. Oracle didn't work out, but attempts continue.
All machine methods are based on remembering history and applying it to the future. Is it so hard to understand that history does not repeat itself.
The most ardent fan of predicting the future is deflated. The oracle failed, but attempts continue.
All machine methods are based on remembering history and applying it to the future. Is it so hard to understand that history does not repeat itself.
+
Illusions are hard for people to part with.
alchemists in search of the philosopher's stone....
Hello to all the invisible warriors!
No one has made a neural network robot for forex yet?
I already did, I think. But in the form of a multicurrency robot.
According to its calculations I have to buy dollar and sell euro.